WizardLM commited on
Commit
ab077af
β€’
1 Parent(s): 366a19a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -25,18 +25,18 @@ pipeline_tag: text-generation
25
 
26
  ## News
27
 
28
- [12/19/2023] πŸ”₯ We released **WizardMath-7B-V1.1** trained from Mistral-7B, the **SOTA 7B math LLM**, achieves **83.2 pass@1** on GSM8k, and **33.0 pass@1** on MATH.
29
 
30
  [12/19/2023] πŸ”₯ **WizardMath-7B-V1.1** outperforms **ChatGPT 3.5**, **Gemini Pro**, **Mixtral MOE**, and **Claude Instant** on GSM8K pass@1.
31
 
32
  [12/19/2023] πŸ”₯ **WizardMath-7B-V1.1** is comparable with **ChatGPT 3.5**, **Gemini Pro**, and surpasses **Mixtral MOE** on MATH pass@1.
33
 
34
- | Model | Checkpoint | Paper | GSM8k | MATH |
35
- | ----- |------| ---- |------|-------|
36
- | **WizardMath-7B-V1.1** | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **83.2** | **33.0** |
37
- | WizardMath-70B-V1.0 | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |
38
- | WizardMath-13B-V1.0 | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |
39
- | WizardMath-7B-V1.0 | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** |
40
 
41
 
42
  ## [12/19/2023] Comparing WizardMath-7B-V1.1 with other open source 7B size math LLMs.
 
25
 
26
  ## News
27
 
28
+ [12/19/2023] πŸ”₯ We released **WizardMath-7B-V1.1** trained from Mistral-7B, the **SOTA 7B math LLM**, achieves **83.2 pass@1** on GSM8k, and **33.0 pass@1** on MATH. Use this [[**Demo**](http://47.103.63.15:50083/)] to chat with it.
29
 
30
  [12/19/2023] πŸ”₯ **WizardMath-7B-V1.1** outperforms **ChatGPT 3.5**, **Gemini Pro**, **Mixtral MOE**, and **Claude Instant** on GSM8K pass@1.
31
 
32
  [12/19/2023] πŸ”₯ **WizardMath-7B-V1.1** is comparable with **ChatGPT 3.5**, **Gemini Pro**, and surpasses **Mixtral MOE** on MATH pass@1.
33
 
34
+ | Model | Checkpoint | Paper | GSM8k | MATH | Demo|
35
+ | ----- |------| ---- |------|-------|-------|
36
+ | **WizardMath-7B-V1.1** | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **83.2** | **33.0** |[[**Demo**](http://47.103.63.15:50083/)] |
37
+ | WizardMath-70B-V1.0 | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** ||
38
+ | WizardMath-13B-V1.0 | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** ||
39
+ | WizardMath-7B-V1.0 | πŸ€— <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | |
40
 
41
 
42
  ## [12/19/2023] Comparing WizardMath-7B-V1.1 with other open source 7B size math LLMs.